Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloNeural reflectance transformation imaging
Anno di pubblicazione2020
Formato-
Autore/iDulecha T. G.; Fanni F. A.; Ponchio F.; Pellacini F.; Giachetti A.
Affiliazioni autoriUniversity of Verona, Verona, Italy; University of Verona, Verona, Italy; CNR-ISTI, Pisa, Italy; Sapienza University of Rome, Rome, Italy; University of Verona, Verona, Italy
Autori CNR e affiliazioni
  • FEDERICO PONCHIO
Lingua/e
  • inglese
AbstractReflectance transformation imaging (RTI) is a computational photography technique widely used in the cultural heritage and material science domains to characterize relieved surfaces. It basically consists of capturing multiple images from a fixed viewpoint with varying lights. Handling the potentially huge amount of information stored in an RTI acquisition that consists typically of 50-100 RGB values per pixel, allowing data exchange, interactive visualization, and material analysis, is not easy. The solution used in practical applications consists of creating "relightable images" by approximating the pixel information with a function of the light direction, encoded with a small number of parameters. This encoding allows the estimation of images relighted from novel, arbitrary lights, with a quality that, however, is not always satisfactory. In this paper, we present NeuralRTI, a framework for pixel-based encoding and relighting of RTI data. Using a simple autoencoder architecture, we show that it is possible to obtain a highly compressed representation that better preserves the original information and provides increased quality of virtual images relighted from novel directions, especially in the case of challenging glossy materials. We also address the problem of validating the relight quality on different surfaces, proposing a specific benchmark, SynthRTI, including image collections synthetically created with physical-based rendering and featuring objects with different materials and geometric complexity. On this dataset and as well on a collection of real acquisitions performed on heterogeneous surfaces, we demonstrate the advantages of the proposed relightable image encoding.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da2161
Pagine a2174
Pagine totali14
RivistaThe visual computer
Attiva dal 1985
Editore: Springer. - Heidelberg
Paese di pubblicazione: Germania
Lingua: inglese
ISSN: 0178-2789
Titolo chiave: The visual computer
Titolo proprio: The visual computer.
Titolo abbreviato: Vis. comput.
Titolo alternativo: Visual computer (Print)
Numero volume della rivista-
Fascicolo della rivista36
DOI10.1007/s00371-020-01910-9
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • ISI Web of Science (WOS) (Codice:000549695100001)
  • Scopus (Codice:2-s2.0-85088145501)
Parole chiaveReflectance transformation imaging, Relighting, Neural network, Autoencoder, Benchmark
Link (URL, URI)https://link.springer.com/article/10.1007/s00371-020-01910-9#author-information
Titolo parallelo-
LicenzaCreative Commons License Attribution 4.0 International (CC BY 4.0)
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • ISTI — Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei-
Allegati
Neural reflectance transformation imaging
Descrizione: OA Published version
Tipo documento: application/pdf